© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15245
    Prev
    Next
    INDEX
    Explanations

    narrative descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.73
     beginnetje
    -0.71
     herum
    -0.65
     argint
    -0.59
    脚注の使い方
    -0.58
     torno
    -0.55
     Audiodateien
    -0.55
     entour
    -0.54
     levure
    -0.54
     ympä
    -0.54
    POSITIVE LOGITS
    boxylic
    0.66
    directly
    0.59
     directly
    0.59
     Ternyata
    0.58
    BeginContext
    0.57
    '}';
    0.55
    🏽
    0.55
     direttamente
    0.54
    ksamkeit
    0.54
     part
    0.53
    Activations Density 0.032%

    No Known Activations